Latent Graph Diffusion: A Unified Framework for Generation and
Prediction on Graphs
- URL: http://arxiv.org/abs/2402.02518v1
- Date: Sun, 4 Feb 2024 15:03:47 GMT
- Title: Latent Graph Diffusion: A Unified Framework for Generation and
Prediction on Graphs
- Authors: Zhou Cai, Xiyuan Wang, Muhan Zhang
- Abstract summary: We first propose Latent Graph Diffusion (LGD), a generative model that can generate node, edge, and graph-level features of all categories simultaneously.
We then formulate prediction tasks including regression and classification as (conditional) generation, which enables our LGD to solve tasks of all levels and all types with provable guarantees.
- Score: 27.542173012315413
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we propose the first framework that enables solving graph
learning tasks of all levels (node, edge and graph) and all types (generation,
regression and classification) with one model. We first propose Latent Graph
Diffusion (LGD), a generative model that can generate node, edge, and
graph-level features of all categories simultaneously. We achieve this goal by
embedding the graph structures and features into a latent space leveraging a
powerful encoder which can also be decoded, then training a diffusion model in
the latent space. LGD is also capable of conditional generation through a
specifically designed cross-attention mechanism. Then we formulate prediction
tasks including regression and classification as (conditional) generation,
which enables our LGD to solve tasks of all levels and all types with provable
guarantees. We verify the effectiveness of our framework with extensive
experiments, where our models achieve state-of-the-art or highly competitive
results across generation and regression tasks.
Related papers
- Large Generative Graph Models [74.58859158271169]
We propose a new class of graph generative model called Large Graph Generative Model (LGGM)
The pre-trained LGGM has superior zero-shot generative capability to existing graph generative models.
LGGM can be easily fine-tuned with graphs from target domains and demonstrate even better performance than those directly trained from scratch.
arXiv Detail & Related papers (2024-06-07T17:41:47Z) - Exploring Task Unification in Graph Representation Learning via Generative Approach [12.983429541410617]
Graphs are ubiquitous in real-world scenarios and encompass a diverse range of tasks, from node-, edge-, and graph-level tasks to transfer learning.
Recent endeavors aim to design a unified framework capable of generalizing across multiple graph tasks.
Among these, graph autoencoders (GAEs) have demonstrated their potential in effectively addressing various graph tasks.
We propose GA2E, a unified adversarially masked autoencoder capable of addressing the above challenges seamlessly.
arXiv Detail & Related papers (2024-03-21T12:14:02Z) - OpenGraph: Towards Open Graph Foundation Models [20.401374302429627]
We develop a general graph foundation model to understand the complex topological patterns present in diverse graph data.
We propose a unified graph tokenizer to adapt our graph model to generalize well on unseen graph data.
We also develop a scalable graph transformer, which effectively captures node-wise dependencies within the global topological context.
arXiv Detail & Related papers (2024-03-02T08:05:03Z) - On the Role of Edge Dependency in Graph Generative Models [28.203109773986167]
We introduce a novel evaluation framework for generative models of graphs.
We focus on the importance of model-generated graph overlap to ensure both accuracy and edge-diversity.
Our results indicate that our simple, interpretable models provide competitive baselines to popular generative models.
arXiv Detail & Related papers (2023-12-06T18:54:27Z) - SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
We present SimTeG, a frustratingly Simple approach for Textual Graph learning.
We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task.
We then generate node embeddings using the last hidden states of finetuned LM.
arXiv Detail & Related papers (2023-08-03T07:00:04Z) - GraphGLOW: Universal and Generalizable Structure Learning for Graph
Neural Networks [72.01829954658889]
This paper introduces the mathematical definition of this novel problem setting.
We devise a general framework that coordinates a single graph-shared structure learner and multiple graph-specific GNNs.
The well-trained structure learner can directly produce adaptive structures for unseen target graphs without any fine-tuning.
arXiv Detail & Related papers (2023-06-20T03:33:22Z) - HiGen: Hierarchical Graph Generative Networks [2.3931689873603603]
Most real-world graphs exhibit a hierarchical structure, which is often overlooked by existing graph generation methods.
We propose a novel graph generative network that captures the hierarchical nature of graphs and successively generates the graph sub-structures in a coarse-to-fine fashion.
This modular approach enables scalable graph generation for large and complex graphs.
arXiv Detail & Related papers (2023-05-30T18:04:12Z) - Hybrid Augmented Automated Graph Contrastive Learning [3.785553471764994]
We propose a framework called Hybrid Augmented Automated Graph Contrastive Learning (HAGCL)
HAGCL consists of a feature-level learnable view generator and an edge-level learnable view generator.
It insures to learn the most semantically meaningful structure in terms of features and topology.
arXiv Detail & Related papers (2023-03-24T03:26:20Z) - A Robust and Generalized Framework for Adversarial Graph Embedding [73.37228022428663]
We propose a robust framework for adversarial graph embedding, named AGE.
AGE generates the fake neighbor nodes as the enhanced negative samples from the implicit distribution.
Based on this framework, we propose three models to handle three types of graph data.
arXiv Detail & Related papers (2021-05-22T07:05:48Z) - Heuristic Semi-Supervised Learning for Graph Generation Inspired by
Electoral College [80.67842220664231]
We propose a novel pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph.
In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art.
arXiv Detail & Related papers (2020-06-10T14:48:48Z) - Adaptive Graph Auto-Encoder for General Data Clustering [90.8576971748142]
Graph-based clustering plays an important role in the clustering area.
Recent studies about graph convolution neural networks have achieved impressive success on graph type data.
We propose a graph auto-encoder for general data clustering, which constructs the graph adaptively according to the generative perspective of graphs.
arXiv Detail & Related papers (2020-02-20T10:11:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.